DeepSeek releases DeepSeek-Coder-V2
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Released DeepSeek-Coder-V2 — 236B (21B active) and 16B (2.4B active) MoE models, further pretrained from a DeepSeek-V2 intermediate checkpoint on 6T additional tokens; programming languages expanded from 86 to 338 and context from 16K to 128K
Why it matters
An open-weight code model that DeepSeek claimed matched GPT-4 Turbo on code-specific tasks
Source — Primary sources first; secondary reports are labelled “Press”
Officialgithub.comhttps://github.com/deepseek-ai/DeepSeek-Coder-V2Added in Week 41, 2026 · See that week
On the map — ⑨ Open-Weight Lineage line
- Previous stopMistral Large
- This recordDeepSeek-Coder-V2
- Next stopEXAONE 3.0
In the model family tree — DeepSeek family · 12 versions
- Earlier versionDeepSeekMath
- This recordDeepSeek-Coder-V2
- Later versionDeepSeek-OCR